Abstract
We investigate the generalization capabilities of neural network–based Ra-man amplifier models. The new proposed model architecture, including fiber parameters as inputs, can predict Raman gains of fiber types unseen during training, unlike previous fiber–specific models.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
D. Zibar, U. C. de Moura, A. M. Rosa Brusin, A. Carena, and F. Da Ros
ci_1_3 The European Conference on Lasers and Electro-Optics (CLEO/Europe) 2021
Uiara C. de Moura, Francesco Da Ros, A. Margareth Rosa Brusin, Andrea Carena, and Darko Zibar
T4B.2 Optical Fiber Communication Conference (OFC) 2020
D. Zibar, A. Ferrari, V. Curri, and A. Carena
M1J.1 Optical Fiber Communication Conference (OFC) 2019